Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access.Elevate landing pages, portfolios, and brand experiences with cinematic web design. Covers parallax storytelling, scroll animations, composition, and performance-conscious animation.
Use when generating or verifying an fp-detector Top Union daily report for a specific local cutoff time, especially when the agent needs to remember the report script, environment loading, timezone/report-time parameters, output file path, and required verification evidence.
Ensure the local Top Union UI for fp-detector is running through the single supported entrypoint at scripts/run_top_union_ui_server.sh ensure. Use when a Codex session needs to open, verify, restart, or troubleshoot the local Top Union review UI against the remote DB without hand-writing python server commands or ad-hoc SSH tunnels.
Supports PyTorch Geometric (PyG) graph neural networks — node/link/graph classification, message passing (GCN, GAT, GraphSAGE, GIN), heterogeneous graphs, neighbor sampling, and custom datasets. Use when working with torch_geometric, not for general NetworkX analytics or non-graph PyTorch models.
Builds and troubleshoots TorchDrug 0.2.1 workflows for molecular graphs, property prediction, self-supervised pretraining, molecule generation, retrosynthesis, protein representation learning, and knowledge graph reasoning. Use when code imports torchdrug or needs its datasets, models, tasks, or Engine.
Implements lane-based enemy pathing, wave spawning, and towers that automatically target and fire. Covers economy and life systems, including wave and economy balancing.
Adds opt_trace() calls to support debugging and profiling. Uses the -t option to enable specific trace tiers and levels.
Convert graded traces and failure examples into SFT training data. Apply rejection sampling to model outputs and construct DPO pairs from passing and failing runs.
Use this skill when creating, managing, or working with Conductor tracks - the logical work units for features, bugs, and refactors. Applies to spec.md, plan.md, and track lifecycle operations.
Create and manage Conductor tracks as work units for features, bugs, and refactors. Covers spec.md, plan.md, and track lifecycle operations.
Uses ADS-B and AIS sources to trace flights, ships, identifiers, ownership, and port-call histories. Analyzes tracking gaps and dark-fleet behavior for sanctions research, supply-chain compliance, asset tracing, and journalism.
Tracks adversary C2 and staging infrastructure by clustering indicators on shared attributes (TLS/JARM, certificate fields, favicon hashes, ASN, registration patterns) to find related hosts. Activates for requests to track adversary infrastructure, cluster C2 servers, or pivot on infrastructure attributes to find related hosts.
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
A name only tells half the story. Search the full description and instructions to find the right fit.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name